Create Artifact Provenance

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, yet the description frames the operation as creating/tagging an artifact with provenance metadata — a state-changing write. This directly conflicts with the read-only annotation, mirroring the calibration's create_record contradiction. No compensating behavioral context (where the tag is persisted, whether a receipt is returned) is given.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no filler; the core purpose is stated immediately. It is terse to the point of under-specification for an 8-parameter tool, but the structure itself is efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 8 parameters, 6 required, 25% schema coverage, and no output schema, this tool demands more explanation than one sentence. Critical concepts — delegation_ref scoping, trust_epoch semantics, valid_until expiry, and the requires_human_execution gate — are not addressed, and the write/read ambiguity is left unresolved.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 25% (8 params, 6 required). The description adds meaning for a few fields — content hash maps to content, 'risk class' maps to risk_class, and 'authoring agent' loosely points at delegation_ref — but leaves intended_use, valid_until, trust_epoch, and requires_human_execution entirely unexplained, so it only partially compensates for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (tag) and resource (agent-generated artifact) and enumerates the metadata being attached (content hash, risk class, authoring agent), so the agent knows what the call accomplishes. It does not differentiate itself from provenance-adjacent siblings such as create_derivation_receipt, create_decision_lineage_receipt, or aps_create_attribution_receipt.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no when-to-use, when-not-to-use, prerequisites, or alternative tool. An agent cannot infer from this text why it would call create_artifact_provenance rather than one of the many other receipt/attestation-creating siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.